ADSP t-SNE - Revision history

Bradley Monk at 23:08, 11 June 2018

2018-06-11T23:08:12Z

← Older revision		Revision as of 16:08, 11 June 2018
Line 2:		Line 2:

	{{SmallBox\|float=right\|clear=none\|margin=0px 0px 8px 18px\|width=170px\|font-size=13px\|Other Analyses\|txt-size=11px\|		{{SmallBox\|float=right\|clear=none\|margin=0px 0px 8px 18px\|width=170px\|font-size=13px\|Other Analyses\|txt-size=11px\|
	1. [[~~ADSP~~\|Intro]]<br>		1. [[AD\|Intro]]<br>
	4. [[~~ADSP~~ Neural Nets\|More Neural Nets]]<br>		4. [[AD Neural Nets\|More Neural Nets]]<br>
	2. [[~~ADSP~~ PCA\|PCA]]<br>		2. [[AD PCA\|PCA]]<br>
	3. [[~~ADSP~~ t-SNE\|t-SNE]]<br>		3. [[AD t-SNE\|t-SNE]]<br>
	5. [[~~ADSP~~ Stats\|Descriptive Statistics]]<br>		5. [[AD Stats\|Descriptive Statistics]]<br>
	}}		}}

	t-SNE models each multi-dim object against a point on a euclidean surface in such a way that similar features are modeled by nearby point functions and dissimilar features are modeled by distant point functions. It then projects these points onto the plane allowing you visualize, what would effectively be, all the interesting principal component combinations - the ones that yield unique clusters - simultaneously.		t-SNE models each multi-dim object against a point on a euclidean surface in such a way that similar features are modeled by nearby point functions and dissimilar features are modeled by distant point functions. It then projects these points onto the plane allowing you visualize, what would effectively be, all the interesting principal component combinations - the ones that yield unique clusters - simultaneously.

	~~Again, this code can be downloaded from the: [https://github.com/subroutines/genos GENOS GIT]~~

	<br> <br> <br>		<br> <br> <br>
Line 27:		Line 25:


	MATDATA = '~~ADSPdata~~.mat';		MATDATA = 'ADdata.mat';
	which(MATDATA)		which(MATDATA)
	load(MATDATA)		load(MATDATA)

	clearvars -except ~~ADSP~~		clearvars -except AD



	%% CARBON COPY MAIN VARIABLES FROM ~~ADSP~~.STRUCT		%% CARBON COPY MAIN VARIABLES FROM AD.STRUCT

	LOCI = ~~ADSP~~.LOCI(:,1:17);		LOCI = AD.LOCI(:,1:17);
	CASE = ~~ADSP~~.CASE;		CASE = AD.CASE;
	CTRL = ~~ADSP~~.CTRL;		CTRL = AD.CTRL;
	PHEN = ~~ADSP~~.PHEN;		PHEN = AD.PHEN;

	clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN		clearvars -except AD LOCI CASE CTRL PHEN


Line 61:		Line 59:


	clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN PHE PHECASE PHECTRL		clearvars -except AD LOCI CASE CTRL PHEN PHE PHECASE PHECTRL


Line 92:		Line 90:


	clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN PHE PHECASE PHECTRL		clearvars -except AD LOCI CASE CTRL PHEN PHE PHECASE PHECTRL


Line 113:		Line 111:


	clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN PHE PHECASE PHECTRL		clearvars -except AD LOCI CASE CTRL PHEN PHE PHECASE PHECTRL


Line 146:		Line 144:


	clc; clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN PHE PHECASE PHECTRL		clc; clearvars -except AD LOCI CASE CTRL PHEN PHE PHECASE PHECTRL
	disp(LOCI(1:9,:))		disp(LOCI(1:9,:))

Line 160:		Line 158:


	clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...		clearvars -except AD LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...
	AMX AMXCASE AMXCTRL		AMX AMXCASE AMXCTRL

Line 180:		Line 178:


	clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...		clearvars -except AD LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...
	AMX AMXCASE AMXCTRL		AMX AMXCASE AMXCTRL

Line 198:		Line 196:
	fprintf('\n %.0f final loci count \n\n',size(AMX,1))		fprintf('\n %.0f final loci count \n\n',size(AMX,1))

	clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...		clearvars -except AD LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...
	AMX AMXCASE AMXCTRL		AMX AMXCASE AMXCTRL

Line 213:		Line 211:
	[ADNN, caMX, coMX] = varmx(AMX,AMXCASE,AMXCTRL,PHE);		[ADNN, caMX, coMX] = varmx(AMX,AMXCASE,AMXCTRL,PHE);

	clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...		clearvars -except AD LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...
	AMX AMXCASE AMXCTRL ADNN		AMX AMXCASE AMXCTRL ADNN

Line 244:		Line 242:


	clearvars -except ~~ADSP~~ LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...		clearvars -except AD LOCI CASE CTRL PHEN PHE PHECASE PHECTRL...
	AMX AMXCASE AMXCTRL ADNN PCAMX		AMX AMXCASE AMXCTRL ADNN PCAMX

Line 265:		Line 263:
	% tSN = tsne(PCAC(:,1:10),'NumDimensions',2,'Theta',.6,'NumPCAComponents',0);		% tSN = tsne(PCAC(:,1:10),'NumDimensions',2,'Theta',.6,'NumPCAComponents',0);
	%		%
	% clearvars -except ~~ADSP~~ GENB LOCI CASE CTRL PHEN AMX AMXCASE AMXCTRL...		% clearvars -except AD GENB LOCI CASE CTRL PHEN AMX AMXCASE AMXCTRL...
	% PHE ADNN PCAMX tSN PCAC PCAS		% PHE ADNN PCAMX tSN PCAC PCAS

Line 283:		Line 281:

	disp('done')		disp('done')
	clearvars -except ~~ADSP~~ GENB LOCI CASE CTRL PHEN AMX AMXCASE AMXCTRL...		clearvars -except AD GENB LOCI CASE CTRL PHEN AMX AMXCASE AMXCTRL...
	PHE ADNN PCAMX tSN PCAC PCAS		PHE ADNN PCAMX tSN PCAC PCAS
	</syntaxhighlight>		</syntaxhighlight>
Line 497:		Line 495:
	<br><br>		<br><br>
	{{SmallBox\|float=left\|clear=none\|margin=0px 0px 8px 18px\|width=50%\|font-size=18px\|Other Analyses\|txt-size=14px\|		{{SmallBox\|float=left\|clear=none\|margin=0px 0px 8px 18px\|width=50%\|font-size=18px\|Other Analyses\|txt-size=14px\|
	1. [[~~ADSP~~\|Intro]]<br>		1. [[AD\|Intro]]<br>
	4. [[~~ADSP~~ Neural Nets\|More Neural Nets]]<br>		4. [[AD Neural Nets\|More Neural Nets]]<br>
	2. [[~~ADSP~~ PCA\|PCA]]<br>		2. [[AD PCA\|PCA]]<br>
	3. [[~~ADSP~~ t-SNE\|t-SNE]]<br>		3. [[AD t-SNE\|t-SNE]]<br>
	5. [[~~ADSP~~ Stats\|Descriptive Statistics]]<br>		5. [[AD Stats\|Descriptive Statistics]]<br>
	}}		}}

Line 512:		Line 510:
	----		----

	[http://www.bradleymonk.com/Category:~~ADSP~~ Category:~~ADSP~~]		[http://www.bradleymonk.com/Category:AD Category:AD]
	[[Category:~~ADSP~~]]		[[Category:AD]]

Bradley Monk at 12:08, 6 February 2018

2018-02-06T12:08:20Z

← Older revision		Revision as of 05:08, 6 February 2018
Line 1:		Line 1:
	t-Distributed Stochastic Neighbor Embedding (tSNE) is a technique like PCA that allows one perform dimensionality reduction for visualization purposes. Supposedly tSNE does better than PCA at revealing clusters in high-dimensional data. Whereas PCA only allows you to visualize two or three components directly against each at the same time -- tSNE uses math magic to coerce a high-dimensional dataset into either a 2D or 3D array.		t-Distributed Stochastic Neighbor Embedding (tSNE) is a technique like PCA that allows one perform dimensionality reduction for visualization purposes. Supposedly tSNE does better than PCA at revealing clusters in high-dimensional data. Whereas PCA only allows you to visualize two or three components directly against each at the same time -- tSNE uses math magic to coerce a high-dimensional dataset into either a 2D or 3D array.

	t-SNE models each multi-dim object against a point on a euclidean surface in such a way that similar features are modeled by nearby point functions and dissimilar features are modeled by distant point functions. It then projects these points onto the plane allowing you visualize, what would effectively be, all the interesting principal component combinations - the ones that yield unique clusters - simultaneously.

	~~Again, this code can be downloaded from the: [https://github.com/subroutines/genos GENOS GIT]~~

	{{SmallBox\|float=right\|clear=none\|margin=0px 0px 8px 18px\|width=170px\|font-size=13px\|Other Analyses\|txt-size=11px\|		{{SmallBox\|float=right\|clear=none\|margin=0px 0px 8px 18px\|width=170px\|font-size=13px\|Other Analyses\|txt-size=11px\|
Line 13:		Line 9:
	}}		}}

	~~<br> <br> <br> <br> <br> <br> <br>~~		t-SNE models each multi-dim object against a point on a euclidean surface in such a way that similar features are modeled by nearby point functions and dissimilar features are modeled by distant point functions. It then projects these points onto the plane allowing you visualize, what would effectively be, all the interesting principal component combinations - the ones that yield unique clusters - simultaneously.

			Again, this code can be downloaded from the: [https://github.com/subroutines/genos GENOS GIT]

			<br> <br> <br>

	==~~tSNE :~~ t-~~Distributed Stochastic Neighbor Embedding~~==		==t-SNE Code==
	----		----
	<br><br>		<br><br>

Bradley Monk at 12:05, 6 February 2018

2018-02-06T12:05:53Z

← Older revision		Revision as of 05:05, 6 February 2018
Line 1:		Line 1:
	~~The Alzheimer's Disease Sequencing Project~~ (~~[https://www.niagads.org/adsp/content/home ADSP]~~) ~~has made available WES data in vcf format. The following~~ is a ~~step~~-~~by-step analysis walkthrough of this dataset~~. ~~Here~~ the ~~ultimate goal is~~ to ~~develop~~ a ~~platform for Alzheimer's Disease diagnosis based on genome sequencing information~~. ~~The data for this analysis can be downloaded here:~~		t-Distributed Stochastic Neighbor Embedding (tSNE) is a technique like PCA that allows one perform dimensionality reduction for visualization purposes. Supposedly tSNE does better than PCA at revealing clusters in high-dimensional data. Whereas PCA only allows you to visualize two or three components directly against each at the same time -- tSNE uses math magic to coerce a high-dimensional dataset into either a 2D or 3D array.

	~~: [https://drive~~.~~google.com/open?id=1e3tIbQhcDUF1vofAwf4oYVOl8XriC44v ADSP_WES_VCF_LATEST_RELEASE.mat]~~.		t-SNE models each multi-dim object against a point on a euclidean surface in such a way that similar features are modeled by nearby point functions and dissimilar features are modeled by distant point functions. It then projects these points onto the plane allowing you visualize, what would effectively be, all the interesting principal component combinations - the ones that yield unique clusters - simultaneously.

	Both the dataset and the following analysis code are in MATLAB format. Note however there is an [https://cran.r-project.org/web/packages/R.matlab/index.html R package] for reading .mat files. All MATLAB code ~~and custom functions used in the demo walkthrough below~~ can be downloaded ~~here:~~		Again, this code can be downloaded from the: [https://github.com/subroutines/genos GENOS GIT]

	: [https://github.com/subroutines/genos GENOS ~~GITHUB CODE REPO~~]

	{{SmallBox\|float=right\|clear=none\|margin=0px 0px 8px 18px\|width=170px\|font-size=13px\|Other Analyses\|txt-size=11px\|		{{SmallBox\|float=right\|clear=none\|margin=0px 0px 8px 18px\|width=170px\|font-size=13px\|Other Analyses\|txt-size=11px\|

Bradley Monk: /* t-SNE Plots */

2018-02-06T11:54:19Z

t-SNE Plots

← Older revision		Revision as of 04:54, 6 February 2018
Line 317:		Line 317:
	axis off		axis off
	</syntaxhighlight>		</syntaxhighlight>
	[[File: TSNE Case Control.png\|~~600px~~]]
	[[File: TSNE Case Control 2kvars.png\|~~600px~~]]		<big>Top 100 variants</big>
			[[File: TSNE Case Control.png\|800px]]

			<big>Top 2000 variants</big>
			[[File: TSNE Case Control 2kvars.png\|800px]]


Line 340:		Line 344:
	axis off		axis off
	</syntaxhighlight>		</syntaxhighlight>
	[[File: TSNE Study Cohort.png\|~~600px~~]]
	[[File: TSNE Study Cohort 2kvars.png\|~~600px~~]]		<big>Top 100 variants</big>
			[[File: TSNE Study Cohort.png\|800px]]

			<big>Top 2000 variants</big>
			[[File: TSNE Study Cohort 2kvars.png\|800px]]


Line 360:		Line 368:
	axis off		axis off
	</syntaxhighlight>		</syntaxhighlight>
	[[File: TSNE Sex.png\|~~600px~~]]
	[[File: TSNE Sex 2kvars.png\|~~600px~~]]		<big>Top 100 variants</big>
			[[File: TSNE Sex.png\|800px]]

			<big>Top 2000 variants</big>
			[[File: TSNE Sex 2kvars.png\|800px]]


Line 392:		Line 404:
	axis off		axis off
	</syntaxhighlight>		</syntaxhighlight>
	[[File: TSNE Age.png\|~~600px~~]]
	[[File: TSNE Age 2kvars.png\|~~600px~~]]		<big>Top 100 variants</big>
			[[File: TSNE Age.png\|800px]]

			<big>Top 2000 variants</big>
			[[File: TSNE Age 2kvars.png\|800px]]


Line 422:		Line 438:
	axis off		axis off
	</syntaxhighlight>		</syntaxhighlight>
	[[File: TSNE APOE.png\|~~600px~~]]
	[[File: TSNE APOE 2kvars.png\|~~600px~~]]		<big>Top 100 variants</big>
			[[File: TSNE APOE.png\|800px]]

			<big>Top 2000 variants</big>
			[[File: TSNE APOE 2kvars.png\|800px]]


Line 444:		Line 464:
	axis off		axis off
	</syntaxhighlight>		</syntaxhighlight>
	[[File: TSNE Consent 2kvars.png\|~~600px~~]]
			<big>Top 2000 variants</big>
			[[File: TSNE Consent 2kvars.png\|800px]]


Line 474:		Line 496:

	<br> <br> <br> <br> <br> <br> <br>		<br> <br> <br> <br> <br> <br> <br>

	==Additional Genomics Analyses==		==Additional Genomics Analyses==
	----		----

Bradley Monk at 11:50, 6 February 2018

2018-02-06T11:50:02Z

Show changes

Bradley Monk: Created page with "The Alzheimer's Disease Sequencing Project ([https://www.niagads.org/adsp/content/home ADSP]) has made available WES data in vcf format. The following is a step-by-step analys..."

2018-02-05T11:42:26Z

Created page with "The Alzheimer's Disease Sequencing Project ([https://www.niagads.org/adsp/content/home ADSP]) has made available WES data in vcf format. The following is a step-by-step analys..."

New page

The Alzheimer's Disease Sequencing Project ([https://www.niagads.org/adsp/content/home ADSP]) has made available WES data in vcf format. The following is a step-by-step analysis walkthrough of this dataset. Here the ultimate goal is to develop a platform for Alzheimer's Disease diagnosis based on genome sequencing information. The data for this analysis can be downloaded here:

: [https://drive.google.com/open?id=1e3tIbQhcDUF1vofAwf4oYVOl8XriC44v ADSP_WES_VCF_LATEST_RELEASE.mat].

Both the dataset and the following analysis code are in MATLAB format. Note however there is an [https://cran.r-project.org/web/packages/R.matlab/index.html R package] for reading .mat files. All MATLAB code and custom functions used in the demo walkthrough below can be downloaded here:

: [https://github.com/subroutines/genos GENOS GITHUB CODE REPO]

{{SmallBox|float=right|clear=none|margin=0px 0px 8px 18px|width=170px|font-size=13px|Other Analyses|txt-size=11px|
1. [[ADSP|Intro]] 
4. [[ADSP Neural Nets|More Neural Nets]] 
2. [[ADSP PCA|PCA]] 
3. [[ADSP t-SNE|t-SNE]] 
5. [[ADSP Stats|Descriptive Statistics]] 
}}

==Additional Genomics Analyses==
----
 
{{SmallBox|float=left|clear=none|margin=0px 0px 8px 18px|width=50%|font-size=18px|Other Analyses|txt-size=14px|
1. [[ADSP|Intro]] 
4. [[ADSP Neural Nets|More Neural Nets]] 
2. [[ADSP PCA|PCA]] 
3. [[ADSP t-SNE|t-SNE]] 
5. [[ADSP Stats|Descriptive Statistics]] 
}}

 

==Notes==
----

[http://www.bradleymonk.com/Category:ADSP Category:ADSP]
[[Category:ADSP]]